Search
Go
Research Assistant on AI Safety
OXFORD · GB
$46K–$51K
Full-time
JUNIOR
About the Role
The University of Oxford's Department of Computer Science is seeking a Research Assistant to join the OATML research group, working on AI technical safety, security, reliability, and robustness. The role involves foundational research on large language models and multimodal foundation models, including safety alignment, adversarial training, jailbreaking, uncertainty quantification, and hallucination. The post is fixed-term until October 2027.
Responsibilities
- Conduct research on AI safety, security, reliability, and robustness for frontier models
- Investigate topics including safety alignment, adversarial training, jailbreaking, uncertainty quantification, and AI hallucination
- Contribute to publishable research and communicate findings at meetings and conferences
- Represent the OATML research group and collaborate with team members
Requirements
- Master's degree (or close to completion) in a relevant field
- Knowledge of foundation models (generative AI), LLM jailbreaking, safety alignment, adversarial machine learning, or deep learning
- Strong programming skills
- Ability to produce and communicate research effectively
Nice to Have
- Experience with large language models and multimodal foundation models
- Published research in relevant areas
University of Oxford
Oxford · GB · 18166+ employees
The University of Oxford is a collegiate research university and the oldest university in the English-speaking world. It is composed of a central university, its academic divisions, departments, faculties, and a collection of self-governing colleges.
